© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12932
    Prev
    Next
    INDEX
    Explanations

    phrases related to complaints or negative feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -0.43
     êtes
    -0.36
    nameLabel
    -0.36
     Erfolgs
    -0.35
    GeneratedCode
    -0.34
     concepto
    -0.33
    beelden
    -0.33
     actively
    -0.33
    skapet
    -0.33
    Ӕ
    -0.32
    POSITIVE LOGITS
    SequentialGroup
    0.64
    setVerticalGroup
    0.60
    zembro
    0.56
    asional
    0.53
     regrettable
    0.53
     CreateTagHelper
    0.52
     difficulties
    0.50
    endpush
    0.50
     unfortunate
    0.49
     guilty
    0.49
    Activations Density 0.183%

    No Known Activations